{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/1a512cbc33474dfc8dc77e5aca241b75\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/1a512cbc33474dfc8dc77e5aca241b75-e454cb2b4ce147ae.gif","duration":522.673,"title":"PayPal Fraud Detection 🕵️‍♂️","description":"In this video, I discuss the process of building a fraud detection model for PayPal users. I outline two primary tasks: identifying frosters based on user profiles and operationalizing the model effectively. I emphasize the importance of data exploration, preparation, and feature engineering, while also addressing the challenges of imbalanced data. Please take note of the strategies I suggest for model evaluation and operationalization, as your input will be valuable in refining our approach."}